UniSim-SLAM: Feed-Forward SLAM with Unified Sim(3) Optimization
zhenjun_zhao · x · 2026-08-04
Accepted at ECCV 2026, UniSim-SLAM addresses geometric inconsistencies and trajectory drift in feed-forward SLAM over long sequences. The system runs lightweight two-view keyframe tracking in the frontend and performs periodic multi-view submap refinement in the backend. By formulating a unified multi-level factor graph on Sim(3), it jointly optimizes global keyframe poses and submap poses. Experiments show it achieves state-of-the-art accuracy in the uncalibrated setting, significantly reducing trajectory error.
More from Research
- Behind NeurIPS Rejections: Limited Physical Space Forces Extra Papers Out — qberthet · 2026-08-04
- Include Standard Libraries in RL Environments to Stop AI Agents Reinventing the Wheel — cephaloform · 2026-08-04
- SimpleAI releases HiFi-UMI: high-fidelity data engine enables direct real-robot deployment without teleoperation data — 机器之心 · 2026-08-04
- Qianxun AI study: legacy data shows 'emergent transfer' after robot hardware upgrades, with a critical threshold — 机器之心 · 2026-08-04
- QuerySplat: Decoupling Geometry and Appearance in 3DGS Prediction — zhenjun_zhao · 2026-08-04
- Target-Free Self-Calibration for Rolling Shutter Cameras — zhenjun_zhao · 2026-08-04